mirror of
https://github.com/tile-ai/tilelang.git
synced 2026-11-03 08:43:38 +08:00
Lei Wang
c750fb8a98
* [Enhancement] Update examples and tests for improved type handling and functionality
- Enhanced various example scripts to support new data types and improve compatibility with PyTorch.
- Updated tests across multiple modules to ensure correct functionality with the latest changes in type handling.
- Refactored code in examples to streamline operations and improve clarity, particularly in tensor operations and memory management.
- Added comprehensive tests for new features and fixed existing issues related to type conversions and buffer handling.
* [Refactor] Update accumulation data type to float32 across examples
- Changed accumulation data type from "float" to T.float32 in multiple example scripts to ensure consistency and improve numerical stability.
- This update affects various modules including flash attention, GEMM analysis, convolution, and deepseek MLA examples, enhancing type handling across the board.
* [Refactor] Standardize data type usage across benchmark scripts
- Updated data type definitions in benchmark scripts to use T.float16 and T.float32 consistently, enhancing clarity and type handling.
- Adjusted dtype assignments in matmul functions and configuration setups to align with the new standard.
- Improved overall code consistency and maintainability by ensuring uniform data type usage across various modules.
* [Refactor] Standardize data type usage in templates and scripts
- Updated data type definitions in various templates and scripts to use string representations (e.g., "float16", "int32") instead of T.float16 and T.int32 for improved consistency and clarity.
- Enhanced overall code maintainability by ensuring uniform data type usage across multiple modules, including convolution, elementwise operations, and matrix multiplication templates.
- This change aims to streamline type handling and improve compatibility with existing workflows.
* [Refactor] Standardize data type usage in examples and benchmarks
- Updated data type definitions in various example and benchmark scripts to use T.float16 and T.int32 consistently, enhancing clarity and maintainability.
- Adjusted dtype assignments in kernel functions and configuration setups to align with the new standard.
- Improved overall code consistency by ensuring uniform data type usage across multiple modules, including attention mechanisms, matrix multiplication, and GEMM examples.
* [Refactor] Import dtypes from language.v2 module
- Added import statement for dtypes from the language.v2 module to enhance type handling and maintain consistency across the codebase.
- This change aims to streamline data type management and improve overall code clarity.
* fix
* [Refactor] Standardize data type usage across scripts
- Updated data type definitions in various scripts to use string representations (e.g., "float16", "int8") instead of T.float16 and T.int8 for improved consistency and clarity.
- Adjusted dtype assignments in functions and configuration setups to align with the new standard, enhancing overall code maintainability.
- This change affects multiple modules, including benchmark and attention mechanisms, ensuring uniform data type usage throughout the codebase.
* [Refactor] Update data type handling for consistency and clarity
- Changed string representations of data types in the Hint class to use T.float32 and T.int32 for improved consistency.
- Added new data types "int4" and "int16" to the dtypes module, enhancing type support across the codebase.
- Updated function signatures and assertions in the lop3 and mxfp modules to utilize the new data types, ensuring uniformity in type handling.
- This refactor aims to streamline data type management and improve overall code clarity and maintainability.
* [Enhancement] Improve data type handling and error messaging
- Introduced a mapping for canonical data types to their display strings, enhancing clarity in type representation.
- Updated the dtype creation logic to utilize the new mapping, ensuring more intuitive handling of string inputs.
- Refined error messages in the lop3 module to provide clearer feedback on invalid source formats, improving debugging and user experience.
* [Fix] Correct boolean flag in GEMM SP test case
- Updated the boolean flag in the test_gemm_sp_sm90 function to ensure proper functionality in the test case.
- This change enhances the accuracy of the test and aligns it with expected behavior for the GEMM SP implementation.
* [Refactor] Standardize data type usage across scripts
- Updated data type definitions in various scripts to use T.float16 and T.bfloat16 consistently, enhancing clarity and maintainability.
- Adjusted dtype assignments in function signatures and argument parsing to align with the new standard, ensuring uniform data type usage throughout the codebase.
- This change affects multiple modules, including benchmarks and examples, improving overall code consistency and readability.
* [Refactor] Standardize data type usage in various modules
- Updated data type assignments in multiple scripts to utilize T.float32, T.int8, and T.int32 consistently, enhancing clarity and maintainability.
- Adjusted function signatures and parameter types across benchmarks, examples, and tests to align with the new standard, ensuring uniform data type usage throughout the codebase.
- This change improves overall code consistency and readability, impacting modules related to matrix multiplication, GEMM, and tensor operations.
* [Refactor] Update argument parsing for data types in benchmarks
- Changed argument parsing for data types in benchmark_matmul_intrinsic.py and benchmark_matmul_sp.py to use string representations ("float16", "int8", "float") instead of T.float16 and T.float.
- This update enhances consistency in data type handling across benchmark scripts, improving clarity and maintainability.
* [Refactor] Update data type handling in benchmark and example scripts
- Changed data type arguments in benchmark and example scripts to use string representations ("float16") instead of T.float16 for improved consistency.
- Updated function signatures and argument parsing to align with the new standard, enhancing clarity and maintainability across the codebase.
- This change affects multiple modules related to attention mechanisms and tensor operations, ensuring uniform data type usage throughout the examples.
* [Refactor] Fix data type conversion in multiple scripts
- Corrected the usage of the data type conversion method from dtype..as_torch() to dtype.as_torch() across various benchmark and example scripts.
- This change enhances consistency in data type handling and improves code readability, impacting modules related to attention mechanisms and tensor operations.
* [Refactor] Update float8 data type usage across multiple scripts
- Changed instances of T.float8_e4m3 to T.float8_e4m3fn in various benchmark, example, and test scripts to ensure consistency in data type handling.
- This update enhances clarity and maintainability across the codebase, particularly in modules related to matrix multiplication and tensor operations.
* [Refactor] Enhance float8 data type handling in CUDA code generation
- Updated the handling of float8 data types in the CUDA code generation to include additional float8 variants, improving type conversion logic.
- Adjusted conditions to ensure proper type checks for float8 conversions, enhancing clarity and maintainability in the codebase.
- Modified layout inference to streamline float8 type checks, ensuring consistency across the implementation.
- This change impacts modules related to matrix operations and CUDA code generation, improving overall type handling and conversion accuracy.
* [Refactor] Streamline float8 data type handling in CUDA and related modules
- Enhanced float8 data type handling in CUDA code generation by refining type conversion logic and ensuring consistent type checks.
- Updated layout inference for float8 types to improve clarity and maintainability across the implementation.
- This change impacts modules related to matrix operations and CUDA code generation, improving overall type handling and conversion accuracy.
* [Refactor] Remove unnecessary cache disabling in float8 example script
- Eliminated the call to tilelang.disable_cache() in example_group_per_split_token_cast_to_fp8.py to streamline the code.
- This change enhances clarity and maintainability of the example script without affecting its functionality.
* [Refactor] Update data type usage in debug print tests
- Changed the argument for dtype in the test_debug_print_buffer function from a string representation to the corresponding T.bool type.
- This update enhances consistency in data type handling within the test suite, improving clarity and maintainability.
* lint fix
* Update function parameter types from `str` to `T.dtype` for improved type safety in attention sink and related examples
* Refactor `gemv_alloc_reducer` function signature for improved readability by formatting parameters across multiple lines.
57 lines
1.9 KiB
Python
57 lines
1.9 KiB
Python
import torch
|
|
import tilelang
|
|
import tilelang.language as T
|
|
|
|
|
|
def ref_program(x, y):
|
|
return x + y
|
|
|
|
|
|
@tilelang.jit(out_idx=[-1])
|
|
def elementwise_add(M, N, block_M, block_N, in_dtype, out_dtype, threads):
|
|
@T.prim_func
|
|
def elem_add(A: T.Tensor((M, N), in_dtype), B: T.Tensor((M, N), in_dtype), C: T.Tensor((M, N), out_dtype)):
|
|
with T.Kernel(T.ceildiv(N, block_N), T.ceildiv(M, block_M), threads=threads) as (bx, by):
|
|
A_shared = T.alloc_shared((block_M, block_N), in_dtype)
|
|
B_shared = T.alloc_shared((block_M, block_N), in_dtype)
|
|
C_local = T.alloc_fragment((block_M, block_N), out_dtype)
|
|
C_shared = T.alloc_shared((block_M, block_N), out_dtype)
|
|
|
|
T.copy(A[by * block_M, bx * block_N], A_shared)
|
|
T.copy(B[by * block_M, bx * block_N], B_shared)
|
|
for local_y, local_x in T.Parallel(block_M, block_N):
|
|
C_local[local_y, local_x] = A_shared[local_y, local_x] + B_shared[local_y, local_x]
|
|
T.copy(C_local, C_shared)
|
|
T.copy(C_shared, C[by * block_M, bx * block_N])
|
|
|
|
return elem_add
|
|
|
|
|
|
def run_elementwise_add(M, N):
|
|
a = torch.randn(M, N, dtype=torch.float32, device="cuda")
|
|
b = torch.randn(M, N, dtype=torch.float32, device="cuda")
|
|
|
|
# Default config
|
|
block_M, block_N = 128, 128
|
|
config = {"block_M": block_M, "block_N": block_N, "threads": 128}
|
|
kernel = elementwise_add(M, N, **config, in_dtype=T.float32, out_dtype=T.float32)
|
|
|
|
out = kernel(a, b)
|
|
torch.testing.assert_close(out, ref_program(a, b), rtol=1e-2, atol=1e-2)
|
|
|
|
code = kernel.get_kernel_source()
|
|
if block_N == N:
|
|
assert "tma_load" in code and "CUtensorMap" not in code
|
|
else:
|
|
assert "tma_load" in code and "CUtensorMap" in code
|
|
|
|
|
|
def main():
|
|
run_elementwise_add(128, 128)
|
|
run_elementwise_add(256, 128)
|
|
run_elementwise_add(256, 256)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|